Run 4. Outer Step 58. Inner Step 25.

config.json

@@ -268,18 +268,14 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586920,
-    5586925,
-    5586929,
-    5586933,
-    5586937
+    5586971
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5584811,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d10c8afefbbd818b5c50d88daf02364f097f5ff9fd85c682f8016012265a7a
+oid sha256:a504e9680756904bd4119ae423c9c52acfe6e2ea9d4659a6d7adedf5948f412e
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8339ad62f67f2283cc2ff5bf8c119cc29a9e48934141598c1f2d56fcbf8b9243
+oid sha256:6f8e29e8796b6ac8045463591296aa74fcadaf97683d554cf16e4dbda8d78e5a
 size 4040701744